Satellite-based ocean monitoring buoy network construction method, device and storage medium

Abstract

The present application discloses a method, device and storage medium for constructing a satellite-based ocean monitoring buoy network. It relates to the field of satellite technology. The method includes: obtaining the node distance between each buoy node and the transmission data volume of each buoy node, wherein the transmission data is the ocean monitoring data information collected by the buoy node for transmission to the satellite; determining the connection probability between each buoy node according to the node distance and the transmission data volume through a preset probability prediction model; determining the connection relationship between each buoy node according to the connection probability based on a preset connection rule, wherein the connection rule is used to exclude the connection relationship of repeated connection, and wherein the connection relationship includes a single-hop relationship and a multi-hop relationship; and constructing an ocean monitoring buoy network according to the connection relationship. The technical problems of the small monitoring range and large network overhead of the ocean monitoring buoy network in the prior art are solved.

Description

Technical Field

[0001] The present application relates to the field of satellite technology, and in particular to a method, device and storage medium for constructing a satellite-based ocean monitoring buoy network. Background Art

[0002] Ocean monitoring buoys are usually composed of buoy bodies, data acquisition modules and communication modules. The data acquisition module can effectively collect various ocean data information and transmit the ocean data information to the receiving end of the shore station through the communication module. At present, the ocean monitoring buoy network composed of ocean monitoring buoys can form a variety of network topologies. The purpose of building an ocean monitoring buoy network is to expand the scope of ocean monitoring, aggregate ocean data information at the aggregation nodes in the network, reduce system energy consumption through a reasonable topology, and achieve long-term monitoring of the target sea area. A stable topology will play a decisive role in the communication of the buoy network.

[0003] Typical ocean monitoring buoy networks include star networks and mesh networks. These networks are usually composed of aggregation nodes and terminal nodes. The aggregation nodes aggregate data in the network and transmit the data to the shore station receiving end via satellite; the terminal nodes transmit information to the aggregation nodes in the star network, while in the mesh network, some terminal nodes also play the role of data routing, which can communicate not only with the aggregation nodes but also with other terminal nodes.

[0004] refer to Figure 1A As shown in the figure, the star network structure is relatively simple, so it has high reliability and is widely used in various communication occasions. The star network uses a single-hop information transmission method, and the communication distance between each node in the network is relatively close, so it cannot meet the monitoring needs of a large range and long distance.

[0005] refer to Figure 1B As shown in the figure, the Mesh network structure layout is more flexible and can be networked through a specific mode, making the buoy network theoretically more robust and reliable than the star network. However, there are complex and repeated connections between the terminal nodes of the Mesh network. The same data packet may be transmitted through multiple paths, resulting in bandwidth waste. In addition, the complex routing algorithm of the Mesh network requires additional computing and storage resources, which increases network overhead.

[0006] The publication number is CN118607417A, and the name is a method, product, medium and equipment for identifying marine environmental risks in coastal areas. It involves the field of environmental risk identification. First, marine environmental monitoring buoys are used to monitor the marine dynamic environmental parameters and meteorological parameters in coastal areas, tide gauges or tidal models are used to monitor the water level in coastal areas, and marine environmental background data acquisition equipment is used to obtain the water depth topography and shore topography in coastal areas. Based on the marine dynamic environmental parameters, meteorological parameters, water level, water depth topography and shore topography, a variety of marine environmental numerical models are constructed, and hydrodynamic environment simulation is performed on coastal areas. The marine environmental numerical model with the smallest simulation error is used as the marine environmental numerical model for commercial operation, which is used to simulate future marine dynamic environmental parameters, and then divide the risk areas in coastal areas.

[0007] The publication number is CN119049227A, and the name is a marine disaster monitoring and early warning system, which includes a data acquisition module, a data processing module, a data analysis module, an early warning release module, an information sharing module and a system management module. By integrating buoys and sensor networks, remote sensing monitoring networks and video monitoring networks, it realizes multi-dimensional and all-round real-time monitoring of the marine environment. It not only covers basic sea conditions data such as temperature, salinity, flow rate, wind speed, wind direction, wave height, etc., but also obtains a wide range of sea area information through satellite and drone technology, and uses video monitoring equipment to capture sea surface conditions in real time, providing comprehensive and reliable data support for accurate early warning and timely response to marine disasters, and significantly improving monitoring efficiency and disaster response capabilities.

[0008] With respect to the technical problems of the small monitoring range and high network overhead of the ocean monitoring buoy network in the prior art, no effective solution has been proposed so far. Summary of the invention

[0009] The embodiments of the present application provide a method, device and storage medium for constructing a satellite-based ocean monitoring buoy network, so as to at least solve the technical problems of the small monitoring range and high network overhead of the ocean monitoring buoy network in the prior art.

[0010] According to one aspect of an embodiment of the present application, a method for constructing a satellite-based ocean monitoring buoy network is provided, including: obtaining the node distance between each buoy node and the transmission data volume of each buoy node, wherein the transmission data is ocean monitoring data information collected by the buoy node for transmission to the satellite; determining the connection probability between each buoy node according to the node distance and the transmission data volume through a preset probability prediction model; determining the connection relationship between each buoy node according to the connection probability based on preset connection rules, wherein the connection rule is used to exclude connection relationships of repeated connections, and wherein the connection relationship includes a single-hop relationship and a multi-hop relationship; and constructing an ocean monitoring buoy network according to the connection relationship.

[0011] According to another aspect of an embodiment of the present application, a satellite-based ocean monitoring buoy network construction device is also provided, including: a data acquisition module, used to obtain the node distance between each buoy node and the transmission data volume of each buoy node, wherein the transmission data is the ocean monitoring data information collected by the buoy node for transmission to the satellite; a probability determination module, used to determine the connection probability between each buoy node according to the node distance and the transmission data volume through a preset probability prediction model; a relationship determination module, used to determine the connection relationship between each buoy node according to the connection probability based on preset connection rules, wherein the connection rule is used to exclude the connection relationship of repeated connection, and wherein the connection relationship includes a single-hop relationship and a multi-hop relationship; and a network generation module, used to construct an ocean monitoring buoy network according to the connection relationship.

[0012] According to another aspect of an embodiment of the present application, a satellite-based ocean monitoring buoy network construction device is also provided, including: a processor; and a memory, connected to the processor, for providing the processor with instructions for processing the following processing steps: obtaining the node distance between each buoy node and the transmission data volume of each buoy node, wherein the transmission data is the ocean monitoring data information collected by the buoy node for transmission to the satellite; determining the connection probability between each buoy node according to the node distance and the transmission data volume through a preset probability prediction model; determining the connection relationship between each buoy node according to the connection probability based on preset connection rules, wherein the connection rule is used to exclude connection relationships of repeated connections, and wherein the connection relationship includes single-hop relationship and multi-hop relationship; and generating an ocean monitoring buoy network according to the connection relationship.

[0013] According to another aspect of an embodiment of the present application, there is also provided an integrated electronic system, including a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the above method.

[0014] According to another aspect of the embodiments of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above method are implemented.

[0015] In the embodiment of the present application, the satellite determines the connection probability between each buoy node according to the distance between each buoy node and the amount of data transmitted through the probability prediction model, so that the satellite dynamically adjusts the connection relationship between the buoy nodes through the probability prediction model, so that the ocean monitoring buoy network can be optimized more accurately, thereby improving the reliability and speed of data transmission. In addition, the technical solution integrates single-hop and multi-hop connection mechanisms. Compared with the star network in the prior art, the technical solution does not limit the connection relationship between the buoy nodes to a single-hop relationship, which not only ensures efficient communication in the local area, but also meets the needs of large-scale data transmission over a large range, effectively overcoming the problem of limited coverage of the traditional star network. In addition, the technical solution screens the connection probability and excludes the connection relationship of repeated connections, avoiding unnecessary data redundancy and bandwidth waste, and there is no need to transmit the transmitted data repeatedly through multiple paths, which significantly reduces the network operation cost and reduces the network overhead. In addition, the technical problems of the small monitoring range and large network overhead of the ocean monitoring buoy network in the prior art are solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0017] Figure 1A It is a schematic diagram of a star network structure in the prior art;

[0018] Figure 1B It is a schematic diagram of a Mesh network structure in the prior art;

[0019] Figure 2 is a hardware structure block diagram for implementing the satellite according to Embodiment 1 of the present application;

[0020] Figure 3 is a schematic diagram of the ocean monitoring system according to Example 1 of the present application;

[0021] Figure 4 It is a flowchart of a method for constructing a satellite-based ocean monitoring buoy network according to the first aspect of Example 1 of the present application;

[0022] Figure 5 is a schematic diagram of an ocean monitoring buoy network according to Example 1 of the present application;

[0023] Figure 6 is a schematic diagram of a probability prediction model according to Example 1 of the present application;

[0024] Figure 7It is a sequential flow diagram of the method for constructing a satellite-based ocean monitoring buoy network according to Example 1 of the present application;

[0025] Figure 8 is a schematic diagram of a satellite-based ocean monitoring buoy network construction device according to Example 2 of the present application; and

[0026] Fig. 9 It is a schematic diagram of a satellite-based ocean monitoring buoy network construction device according to Example 3 of the present application. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the technical solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only embodiments of a part of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work should fall within the scope of protection of the present application.

[0028] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0029] Example 1

[0030] According to this embodiment, a method embodiment of a method for constructing a satellite-based ocean monitoring buoy network is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0031] Figure 2 A schematic diagram showing the hardware architecture of the satellite. Figure 2As shown, satellite 200 includes an integrated electronic system, which includes: a processor, a memory, a bus management module and a communication interface. The memory is connected to the processor, so that the processor can access the memory, read the program instructions stored in the memory, read data from the memory or write data to the memory. The bus management module is connected to the processor and is also connected to a bus such as a CAN bus. Therefore, the processor can communicate with the satellite-borne peripherals connected to the bus through the bus managed by the bus management module. In addition, the processor is also connected to communication devices such as cameras, star sensors, measurement and control transponders, and data transmission equipment via the communication interface. It can be understood by those skilled in the art that Figure 2 The structure shown is for illustration only and does not limit the structure of the above electronic device. Figure 2 More or fewer components as shown, or with Figure 2 Different configurations are shown.

[0032] It should be noted that Figure 2 The one or more processors and / or other data processing circuits shown in the figure may generally be referred to as "data processing circuits" herein. The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computing device. As involved in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0033] Figure 2 The memory shown in the figure can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the method for building a satellite-based ocean monitoring buoy network in the embodiment of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, the method for building a satellite-based ocean monitoring buoy network of the above-mentioned application program is realized. The memory may include a high-speed random access memory and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory.

[0034] It should be noted that, in some optional embodiments, the above Figure 2 The devices shown may include hardware elements (including circuits), software elements (including computer code stored on a computer-readable medium), or a combination of both hardware and software elements. Figure 2 This is merely one example of a particular embodiment and is intended to illustrate the types of components that may be present in the above described apparatus.

[0035] Figure 3 is a schematic diagram of the ocean monitoring system according to this embodiment. Figure 3 As shown, the system includes: buoy nodes 101~10n, a satellite 200 and a shore station receiving terminal 300.

[0036] The buoy nodes 101 - 10n are used to collect ocean monitoring data, including water temperature, conductivity, salinity, etc. The buoy nodes 101 - 10n then transmit the ocean monitoring data to the satellite 200 .

[0037] The same buoy node transmits the same amount of data at different times, for example, the amount of data transmitted by buoy node 101 at the first moment is the same as the amount of data transmitted at the second moment. Different buoy nodes collect different ocean monitoring data, so the amount of data transmitted by different buoy nodes is also different. For example, buoy node 101 is only used to collect water temperature and conductivity, while buoy node 102 is used to collect data such as water temperature, conductivity, salinity, plankton quantity, type and growth rate.

[0038] The satellite 200 is used to transmit ocean monitoring data to a shore station receiving terminal 300 .

[0039] In the above operating environment, according to the first aspect of this embodiment, a method for constructing a satellite-based ocean monitoring buoy network is provided. The method comprises: Figure 3 The satellite 200 shown in FIG. Figure 4 A schematic diagram showing the process of the method is shown in FIG. Figure 4 As shown, the method includes:

[0040] S402: Acquire the node distance between each buoy node and the transmission data volume of each buoy node, wherein the transmission data is the ocean monitoring data information collected by the buoy node for transmission to the satellite;

[0041] S404: Determine the connection probability between each buoy node according to the node distance and the amount of transmitted data through a preset probability prediction model;

[0042] S406: determining the connection relationship between each buoy node according to the connection probability based on a preset connection rule, wherein the connection rule is used to exclude the connection relationship of repeated connection, and wherein the connection relationship includes a single-hop relationship and a multi-hop relationship; and

[0043] S408: Construct an ocean monitoring buoy network based on the connection relationship.

[0044] Specifically, buoy nodes 101 to 10 n Satellite 200 determines buoy nodes 101~10 n The distance between nodesd i,j .in d i,j Indicates i The buoy node and j The satellite 200 obtains the distance between the buoy nodes 101 to 10 received by the satellite 200 at a certain historical moment. n The amount of ocean monitoring data transmitted a i .in a i Indicates i The amount of data transmitted by each buoy node, i =1~ n , j =1~ n .

[0045] Furthermore, the satellite 200 is pre-set with a probability prediction model for predicting the connection probability between each buoy node. Thus, the satellite 200 inputs the node distance and the amount of transmitted data into the probability prediction model, processes the node distance and the amount of transmitted data through the probability prediction model, and outputs the connection probability between each buoy node. .in p i,j Indicates i The buoy node and j The connection probability between the buoy nodes.

[0046] Furthermore, the satellite 200 calculates the connection probability between each buoy node according to the preset connection rule. p i,j Filter to exclude the connection probability of repeated connections. p i,j ,exclude i = j That is, the connection probability of the same buoy node connection, including p 1,1 , p 2,2 ,..., p n,n For example, satellite 200 has selected the connection probability p 1,2 , then exclude p 2,1 .

[0047] After that, the satellite will connect to the buoy nodes corresponding to the selected connection probability, thereby generating single-hop and multi-hop relationships between the buoy nodes. A single-hop relationship is a connection relationship between two buoy nodes directly connected, and a multi-hop relationship is a connection relationship between two buoy nodes connected through other buoy nodes greater than or equal to 1.

[0048] For example, the connection probability obtained by screening includes at least p 1,5 and p 2,5 Then the connection probability p 1,5 The corresponding buoy nodes are buoy node 101 and buoy node 105. The satellite connects buoy node 101 and buoy node 105, so the connection relationship between buoy node 101 and buoy node 105 is a single-hop relationship. Connection probability p 2,5 The corresponding buoy nodes are buoy node 102 and buoy node 105. Satellite 200 connects buoy node 102 and buoy node 105, and the connection relationship between buoy node 102 and buoy node 105 is a single-hop relationship. For another example, buoy node 101 and buoy node 105 are connected to generate a single-hop relationship, buoy node 102 and buoy node 105 are connected to generate a single-hop relationship, and buoy node 102 and buoy node 101 are connected through buoy node 105, so buoy node 102 and buoy node 101 generate a multi-hop relationship.

[0049] Furthermore, the satellite 200 connects the buoy nodes corresponding to the selected connection probabilities, thereby generating a network consisting of buoy nodes 101 to 10 n A network of ocean monitoring buoys (such as Figure 5 As shown in FIG. 1 ). The satellite 200 determines a buoy node in the ocean monitoring buoy network as a collection node, for example, the buoy node 101. Then, each buoy node 101 to 10 n After collecting the ocean monitoring data, the ocean monitoring data is transmitted to the aggregation node through the buoy nodes connected to it, and the aggregation node transmits the ocean monitoring data to the buoy nodes 101~10 n The transmission data is transmitted to the satellite 200. Then the satellite 200 transmits the received transmission data to the shore station receiving end 300, and the shore station receiving end 300 processes the transmission data.

[0050] As described in the background technology, typical ocean buoy network structures include star networks and Mesh These networks are usually composed of aggregation nodes and terminal nodes. The aggregation nodes aggregate the data in the network and transmit the data to the receiving end of the shore station via satellite; the terminal nodes transmit the information to the aggregation nodes in the star network, and MeshIn the network, some terminal nodes also play the role of data routing, which can communicate not only with the aggregation node but also with other terminal nodes. Refer to Figure 1 A As shown in Figure 1, the star network structure is relatively simple, so it has high reliability and is widely used in various communication occasions. The star network uses a single-hop information transmission method, and the communication distance between each node in the network is relatively close, so it cannot meet the monitoring needs of a large range and long distance. Refer to Figure 1 B As shown, Mesh The network structure layout is relatively flexible and can be networked through a specific mode, making the buoy network theoretically more robust and reliable than a star network. Mesh There are complex and repeated connections between each terminal node in the network. The same data packet may be transmitted through multiple paths, resulting in bandwidth waste and Mesh Complex network routing algorithms require additional computing and storage resources, increasing network overhead.

[0051] In view of the technical problems described above, through the technical solution of the embodiment of the present application, the satellite determines the connection probability between each buoy node according to the distance between each buoy node and the amount of data transmitted through the probability prediction model, so that the satellite dynamically adjusts the connection relationship between the buoy nodes through the probability prediction model, so that the ocean monitoring buoy network can be more accurately optimized, thereby improving the reliability and speed of data transmission. In addition, this technical solution integrates single-hop and multi-hop connection mechanisms. Compared with the star network in the prior art, this technical solution does not limit the connection relationship between buoy nodes to a single-hop relationship, which not only ensures efficient communication in the local area, but also meets the needs of large-scale data transmission over a large range, effectively overcoming the problem of limited coverage of the traditional star network. In addition, this technical solution screens the connection probability and excludes the connection relationship of repeated connections, avoiding unnecessary data redundancy and bandwidth waste, and there is no need to transmit the transmitted data repeatedly through multiple paths, which significantly reduces the network operation cost and reduces the network overhead. In addition, the technical problems of the small monitoring range and large network overhead of the ocean monitoring buoy network in the prior art are solved.

[0052] Optionally, the operation of determining the connection probability between each buoy node according to the node distance and the amount of transmitted data through a preset probability prediction model includes: generating a first tensor according to the node distance and the amount of transmitted data; and determining the connection probability between each buoy node according to the first tensor through the probability prediction model.

[0053] Specifically, the satellite 200 determines the buoy nodes 101 to 10 n The distance between nodes .in d i,j Indicates i The buoy node andj The satellite 200 obtains the distance between the buoy nodes 101 to 10 received by the satellite 200 at a certain historical moment. n The amount of ocean monitoring data transmitted a 1 , a 2 ,... a n ] T .in a i Indicates i The amount of data transmitted by each buoy node, i =1~ n , j =1~ n .

[0054] Furthermore, the satellite 200 increases the distance between nodes and the amount of data transferred[ a 1 , a 2 ,... a n ] T Generate the first tensor H ={ D , B}.in B According to the amount of data transmitted [ a 1 , a 2 ,... a n ] T The generated distance from the node D Matrices of the same dimension.

[0055] Furthermore, the satellite 200 transmits the first tensor H ={ D , B} Input to the probability prediction model, process the first tensor through the probability prediction model, and output the connection probability between each buoy node .in p i,j Indicates i The buoy node and j The connection probability between the buoy nodes.

[0056] Therefore, this technical solution uses the first tensor generated by the node distance and transmission data volume that reflects the location distribution and data transmission characteristics between buoy nodes as the input data of the probability prediction model, so that the connection possibility between different buoy nodes can be accurately evaluated through in-depth analysis of the first tensor by the probability prediction model.

[0057] Optionally, the operation of generating a first tensor based on node distance and transmission data volume includes: generating a first matrix based on the ratio between the transmission data volume of the buoy node and the node distance of the corresponding buoy node; generating a second matrix based on the node distance of each buoy node; and stacking the first matrix and the second matrix to generate a first tensor.

[0058] Specifically, the signal attenuates as the distance increases, resulting in a decrease in the signal-to-noise ratio, which in turn affects the data transmission rate and quality. Therefore, the transmission distance indirectly affects the data transmission rate. a i And the node distance of the corresponding buoy node d i,j The ratio between them generates the first matrix .

[0059] in b i,j Indicates i The amount of data transmitted by each buoy node a i With i The buoy nodes and j The node distance between buoy nodes d i,j The ratio between b i,j = a i / d i,j .

[0060] For example b 1,1 Indicates the amount of data transmitted by the first buoy node (i.e., buoy node 101) a 1 The node distance between the first buoy node (i.e., buoy node 101) and the first buoy node (i.e., buoy node 101) d 1,1 The ratio between b 1,1 = a 1 / d 1,1 ;

[0061] b 1,2 Indicates the amount of data transmitted by the first buoy node (i.e., buoy node 101) a 1 The node distance between the first buoy node (ie, buoy node 101) and the second buoy node (ie, buoy node 102) d 1,2 The ratio between b 1,2 = a 1 / d 1,2 ;

[0062] …

[0063] b 1,n Indicates the amount of data transmitted by the first buoy node (i.e., buoy node 101) a 1 With the first buoy node (i.e., buoy node 101) and the n The node distance between buoy nodes (i.e., buoy node 10n) d 1,n The ratio between b 1,n = a 1 / d 1,n .

[0064] For example b 2,1 Indicates the amount of data transmitted by the second buoy node (i.e., buoy node 102) a 2 The node distance between the second buoy node (ie, buoy node 102) and the first buoy node (ie, buoy node 101) d 2,1 The ratio between b 2,1 = a 2 / d 2,1 ;

[0065] b 2,2 Indicates the amount of data transmitted by the second buoy node (i.e., buoy node 102) a 2 The node distance between the second buoy node (ie, buoy node 102) and the second buoy node (ie, buoy node 102) d 2,2 The ratio between b2,2 = a 2 / d 2,2 ;

[0066] …

[0067] b 2,n Indicates the amount of data transmitted by the second buoy node (i.e., buoy node 102) a 2 With the second buoy node (i.e., buoy node 102) and the n The node distance between buoy nodes (i.e., buoy node 10n) d 2,n The ratio between b 2,n = a 2 / d 2,n .

[0068] …

[0069] For example b n,1 Indicates n The amount of data transmitted by each buoy node a n With n The node distance between the first buoy node (ie, buoy node 10n) and the first buoy node (ie, buoy node 101) d n,1 The ratio between b n,1 = a n / d n,1 ;

[0070] b n,2 Indicates n The amount of data transmitted by a buoy node (i.e., buoy node 10n) a n With n The node distance between the first buoy node (ie, buoy node 10n) and the second buoy node (ie, buoy node 102) d n,2 The ratio between b 2n,2 = a n / d n,2 ;

[0071] …

[0072] b n,n Indicates n The amount of data transmitted by a buoy node (i.e., buoy node 10n) a n With n The buoy node (ie, buoy node 10n) and the n The node distance between buoy nodes (i.e., buoy node 10n) d n,n The ratio between b n,n = a n / d n,n .

[0073] Furthermore, the satellite 200 increases the distance between nodes d i,j Generate the second matrix , then the satellite 200 will be the first matrix and the second matrix Stack and generate the first tensor . The first tensor is a rank 3 tensor.

[0074] Therefore, this technical solution generates a first matrix by calculating the ratio of the amount of data transmitted by the buoy node to the distance of the corresponding node, and stacks it with the node distance matrix to form a three-dimensional first tensor. Therefore, this technical solution not only retains the complete information of the original data, but also facilitates the subsequent probability prediction model to perform in-depth analysis and processing, so as to more comprehensively and accurately capture the complex associations between buoy nodes, thereby realizing a refined prediction of the network connection probability.

[0075] Optionally, the operation of determining the connection probability between each buoy node according to the first tensor through the probability prediction model includes: extracting features from the first tensor through the codec network of the probability prediction model to generate a second tensor, wherein the second tensor is used to indicate the connection integral value and the non-connection integral value between the nodes; and softmax The classifier determines the connection probability between each buoy node based on the second tensor.

[0076] Specifically, the probability prediction model preset by the satellite 200 includes a codec network and softmax Classifier. And refer to Figure 6As shown, the codec network includes an encoding network and a decoding network. The encoding network includes an encoding module 1, and the encoding module 1 includes a convolution layer and a maximum pooling layer. The decoding network includes a decoding module 1 and a decoding module 2, wherein the decoding module 1 includes a convolution layer and an upsampling layer, and the decoding module 2 includes an aggregation layer, a convolution layer, an upsampling layer, and a binary classifier. In addition, the codec network also includes a skip layer connection module 1 and a skip layer connection module 2 provided with a fully connected layer.

[0077] Satellite 200 inputs the first tensor into the codec network, and the codec network performs a convolution operation on the probability map through the convolution layer of the encoding module 1 to generate a first feature map. Then the maximum pooling layer of the encoding module 1 performs pooling processing on the first feature map to generate a second feature map. Then the codec network inputs the second feature map output by the encoding module 1 to the skip connection module 1 and the skip connection module 2 respectively. Then the fully connected layer of the skip connection module 1 processes the input second feature map to generate a third feature map, and the fully connected layer of the skip connection module 2 processes the input second feature map to generate a fourth feature map.

[0078] Furthermore, the codec network inputs the third feature map into the decoding module 1 of the decoding network, performs a convolution operation through the convolution layer of the decoding module 1, and generates a fifth feature map. Then, the upsampling layer of the decoding module 1 performs an upsampling operation on the fifth feature map to generate a sixth feature map. Then, the codec network inputs the sixth feature map output by the decoding module 1 into the decoding module 2, and inputs the fourth feature map output by the skip connection module 2 into the decoding module 2.

[0079] Then the decoding module 2 concatenates the sixth feature map and the fourth feature map through the aggregation layer to generate the seventh feature map. Then the convolution layer of the decoding module 2 performs a convolution operation on the seventh feature map to generate the eighth feature map. Then the upsampling layer of the decoding module 2 processes the eighth feature map to generate the second tensor Q ={ C , G}, where the second tensor contains the connection integral values ​​between the float nodes And the non-connected integral value .in c i,j Indicates i The buoy nodes and j The integral value of the connection between the buoy nodes, g i,j Indicates i The buoy nodes and j The integral value of the disconnected buoy nodes.

[0080] And the connection integral value c 1,1 ,c 2,2 ,..., c n,n The position is preset to 0, that is . Non-connected integral value g 1,1 , g 2,2 ,..., g n,n The position is preset to 0, that is .

[0081] Further, the satellite 200 inputs the second tensor into the probability prediction model softmax Classifier, through softmax The classifier determines the connection probability between each buoy node based on the second tensor . The connection probability p 1,1 , p 2,2 ,..., p n,n is 0, that is .

[0082] In addition, the satellite 200 collects sample data in advance, wherein the sample data includes input samples generated according to the sample node distance and the sample transmission data volume, and the corresponding sample connection probability as the output sample. Then, the satellite uses the gradient descent algorithm to train the probability prediction model according to the sample data, thereby training a probability prediction model that can be put into use.

[0083] Therefore, this technical solution effectively extracts key feature information from the first input tensor through multi-level convolution, pooling and upsampling operations through the encoder-decoder network, and generates a second tensor that reflects the potential connection relationship between nodes. softmax The classifier accurately estimates the connection probability between each buoy node based on the connection integral value and the non-connection integral value in the second tensor.

[0084] Optionally, the operation of determining the connection relationship between each buoy node based on the connection probability based on a preset connection rule includes: sorting the connection probabilities to generate a probability sequence; filtering the connection probabilities that meet the connection rules from the probability sequence in turn according to the connection rules; and establishing a connection relationship between the buoy nodes corresponding to the filtered connection probabilities.

[0085] Specifically, the connection probability of satellite 200 pairs is p 1,1 ~ p n,n Sort in descending order to generate a probability sequence. Assume p1,5 exist p 1,1 ~ p n,n The highest probability is p 1,1 , p 2,2 ,..., p n,n If it is 0, the probability is the smallest. Then the probability sequence can be, for example, p 1,5 , p 2,5 , p 5,2 , p 1,2 ,..., p 1,1 , p 2,2 ,..., p n,n .

[0086] Furthermore, the satellite 200 is from the probability sequence p 1,5 , p 2,5 , p 5,2 , p 1,2 ,..., p n,n The connection probabilities that meet the connection rules are screened in turn, and the buoy nodes corresponding to the screened connection probabilities are connected.

[0087] Therefore, this technical solution sorts the connection probabilities between all buoy nodes in descending order, and based on the preset connection rules, screens the sorted probability sequences one by one, so as to quickly eliminate the connection probabilities that do not meet the conditions.

[0088] Optionally, the operation of sequentially screening connection probabilities that meet the connection rules from the probability sequence according to the connection rules includes: sequentially taking the connection probabilities in the probability sequence as target connection probabilities; determining whether the buoy node corresponding to the target connection probability has formed a single-hop relationship in the previous connection probabilities, and excluding the target connection probability when a single-hop relationship is formed; and determining whether the buoy node corresponding to the target connection probability has formed a multi-hop relationship in the previous connection probabilities, and excluding the target connection probability when a multi-hop relationship is formed.

[0089] Specifically, the connection rules include: (1) excluding the target connection probability when the buoy node corresponding to the target connection probability has formed a single-hop relationship in the previous connection probability;

[0090] (2) If the buoy node corresponding to the target connection probability has formed a multi-hop relationship in the previous connection probability, the target connection probability is excluded;

[0091] (3) After all buoy nodes have established connection relationships, the remaining connection probabilities are eliminated.

[0092] For example, the probability sequence is p 1,5 , p 2,5 , p 5,2 , p 1,2 ,..., p n,n The satellite 200 sequentially uses each connection probability in the probability sequence as a target connection probability, and then determines whether the target connection probability needs to be excluded according to the connection rule.

[0093] First, Satellite 200 will p 1,5 As the target connection probability, the target connection probability is then determined p 1,5 Whether the corresponding buoy nodes (i.e., buoy nodes 101 and buoy nodes 105) have formed a single-hop relationship in the front connection probability. The front connection probability is the connection probability that is before the target connection probability in the probability sequence. p 1,5 is the first connection probability in the probability sequence, so there is no previous connection probability. p 1,5 Exclude, and establish a single-hop relationship between the corresponding buoy node 101 and the buoy node 105. In addition, buoy node 101 is the first buoy node used to construct the ocean monitoring buoy network in the probability sequence, and the satellite 200 uses buoy node 101 as the central node (ie, the aggregation node) for constructing the ocean monitoring buoy network.

[0094] Furthermore, Satellite 200 will p 2,5 As the target connection probability, the target connection probability is then determined p 2,5 Whether the corresponding buoy nodes (i.e., buoy nodes 102 and buoy nodes 105) have formed a single-hop relationship in the previous connection probability. p 2,5 The probability of the front column connection is p 1,5 , and the front column connection probability p 1,5The single-hop relationship formed by buoy node 101 is only between buoy node 105. Therefore, buoy node 102 and buoy node 105 do not form a single-hop relationship in the front column connection probability.

[0095] Then, the satellite 200 determines the target connection probability. p 2,5 If the corresponding buoy nodes (i.e., buoy nodes 102 and buoy nodes 105) do not form a single-hop relationship in the previous connection probability, the target connection probability will be determined. p 2,5 Whether the corresponding buoy nodes (i.e., buoy nodes 102 and buoy nodes 105) have formed a multi-hop relationship in the previous connection probability, and if a multi-hop relationship is formed, the target connection probability is excluded. p 2,5 The probability of the front column connection is p 1,5 , and the front column connection probability p 1,5 The corresponding buoy node 101 and buoy node 105 also only form a single-hop relationship, so the buoy node 102 and the buoy node 105 do not form a multi-hop relationship in the front column connection probability, so the satellite 200 does not connect the target probability p 2,5 exclude and p 2,5 The corresponding buoy node 102 and buoy node 105 form a single-hop relationship. In addition, since the buoy node 101 and buoy node 105 have previously established a single-hop relationship, the buoy node 101 and buoy node 102 form a multi-hop relationship.

[0096] Furthermore, Satellite 200 will p 5,2 As the target connection probability, the target connection probability is then determined p 5,2 Whether the corresponding buoy nodes (i.e., buoy nodes 102 and buoy nodes 105) have formed a single-hop relationship in the previous connection probability. p 5,2 The probability of the front column connection is p 1,5 and p 2,5 , and the front column connection probability p 2,5 The corresponding buoy node 102 and buoy node 105 have formed a single-hop relationship, so the satellite 200 will connect the target probability p 5,2 Filter out from the probability sequence.

[0097] Furthermore, Satellite 200 willp 1,2 As the target connection probability, the target connection probability is then determined p 1,2 Whether the corresponding buoy nodes (i.e., buoy nodes 101 and buoy nodes 102) have formed a single-hop relationship in the previous column probability. p 5,2 The probability of the front column connection is p 1,5 and p 2,5 Therefore, the buoy nodes that form a single-hop relationship are buoy node 101 and buoy node 105, and buoy node 102 and buoy node 105. Therefore, buoy node 101 and buoy node 102 do not form a single-hop relationship in the front column connection probability.

[0098] Then, the satellite 200 determines the target connection probability. p 1,2 If the corresponding buoy nodes (i.e., buoy nodes 101 and buoy nodes 102) do not form a single-hop relationship in the previous connection probability, the target connection probability will be determined. p 1,2 Whether the corresponding buoy nodes (i.e., buoy nodes 101 and buoy nodes 102) have formed a multi-hop relationship in the previous connection probability, and if a multi-hop relationship is formed, the target connection probability is excluded. p 5,2 The probability of the front column connection is p 1,5 and p 2,5 Therefore, the buoy node 101 and the buoy node 105, and the buoy node 102 and the buoy node 105 form a single-hop relationship, and the buoy node 101 and the buoy node 102 have formed a multi-hop relationship. p 1,2 Filter out from the probability sequence.

[0099] Furthermore, when the satellite 200 sequentially screens the connection probabilities in the probability sequence and constructs the connection relationship between the buoy nodes, when determining the buoy nodes 101 to 10 n After all the connection relationships are established, the remaining connection probabilities in the probability sequence that have not yet been judged to meet the connection rules are screened out, where the screened connection probabilities at least include those with a connection probability of 0 and are sorted at the end of the probability sequence. p 1,1 , p 2,2 ,..., p n,n .

[0100] Therefore, the technical solution reduces repeated connections by screening the connection probabilities in the probability sequence one by one, thereby quickly determining the connection relationship of each buoy node with the maximum connection probability that can connect all buoy nodes.

[0101] In summary, reference Figure 7 As shown, the sequential steps to build an ocean monitoring buoy network are as follows:

[0102] S701: The satellite 200 obtains the node distance between each buoy node and the transmission data volume of each buoy node;

[0103] S702: The satellite 200 generates a first matrix according to the transmission data volume of the buoy nodes and the ratio between the node distances of the corresponding buoy nodes;

[0104] S703: The satellite 200 generates a second matrix according to the node distances of each buoy node;

[0105] S704: The satellite 200 stacks the first matrix and the second matrix to generate a first tensor;

[0106] S705: The satellite 200 extracts features from the first tensor through an encoder-decoder network of the probability prediction model to generate a second tensor;

[0107] S706: The satellite 200 determines the connection probability between each buoy node according to the second tensor through the softmax classifier of the probability prediction model;

[0108] S707: the satellite 200 sorts the connection probabilities to generate a probability sequence;

[0109] S708: The satellite 200 sequentially uses the connection probabilities in the probability sequence as target connection probabilities;

[0110] S709: The satellite 200 determines whether the buoy node corresponding to the target connection probability has formed a single-hop relationship in the previous connection probability, and if a single-hop relationship is formed, excludes the target connection probability;

[0111] S710: The satellite 200 determines whether the buoy node corresponding to the target connection probability has formed a multi-hop relationship in the previous connection probability, and if a multi-hop relationship is formed, excludes the target connection probability;

[0112] S711: The satellite 200 establishes a connection relationship with the buoy nodes corresponding to the screened connection probabilities;

[0113] S712: The satellite 200 generates an ocean monitoring buoy network according to the connection relationship.

[0114] In addition, according to a second aspect of this embodiment, an integrated electronic system is provided, including a memory, a processor, and a computer program stored in the memory, and the processor executes the computer program to implement the steps of the above method.

[0115] In addition, according to a third aspect of this embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0116] Therefore, according to this embodiment, the satellite determines the connection probability between each buoy node according to the distance between each buoy node and the amount of data transmitted through the probability prediction model, so that the satellite dynamically adjusts the connection relationship between the buoy nodes through the probability prediction model, so that the ocean monitoring buoy network can be optimized more accurately, thereby improving the reliability and speed of data transmission. In addition, this technical solution integrates single-hop and multi-hop connection mechanisms. Compared with the star network in the prior art, this technical solution does not limit the connection relationship between buoy nodes to a single-hop relationship, which not only ensures efficient communication in the local area, but also meets the needs of large-scale data transmission in a large range, effectively overcoming the problem of limited coverage of the traditional star network. In addition, this technical solution screens the connection probability and excludes the connection relationship of repeated connections, avoiding unnecessary data redundancy and bandwidth waste, and does not need to transmit the transmitted data repeatedly through multiple paths, which significantly reduces the network operation cost and reduces the network overhead. In addition, the technical problems of small monitoring range and large network overhead of the ocean monitoring buoy network in the prior art are solved.

[0117] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0118] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0119] Example 2

[0120] Figure 8 The satellite-based ocean monitoring buoy network construction device 800 according to this embodiment is shown, and the device 800 corresponds to the method according to the first aspect of embodiment 1. Figure 8 As shown, the device 800 includes: a data acquisition module 810, which is used to obtain the node distance between each buoy node and the transmission data volume of each buoy node, wherein the transmission data is the ocean monitoring data information collected by the buoy node for transmission to the satellite; a probability determination module 820, which is used to determine the connection probability between each buoy node according to the node distance and the transmission data volume through a preset probability prediction model; a relationship determination module 830, which is used to determine the connection relationship between each buoy node according to the connection probability based on a preset connection rule, wherein the connection rule is used to exclude the connection relationship of repeated connection, and wherein the connection relationship includes a single-hop relationship and a multi-hop relationship; and a network generation module 840, which is used to construct an ocean monitoring buoy network according to the connection relationship.

[0121] Optionally, the probability determination module 820 includes: a first generation submodule, used to generate a first tensor according to the node distance and the amount of transmitted data; and a first determination submodule, used to determine the connection probability between each buoy node according to the first tensor through a probability prediction model.

[0122] Optionally, the first generation submodule includes: a first generation unit, used to generate a first matrix according to the ratio between the transmission data volume of the buoy node and the node distance of the corresponding buoy node; a second generation unit, used to generate a second matrix according to the node distance of each buoy node; and a third generation unit, used to stack the first matrix and the second matrix to generate a first tensor.

[0123] Optionally, the first determination submodule includes: a fourth generation unit, used to perform feature extraction on the first tensor through the encoder-decoder network of the probability prediction model to generate a second tensor, wherein the second tensor is used to indicate the connection integral value and the non-connection integral value between the buoy nodes; and a first determination unit, used to determine the connection probability between each buoy node according to the second tensor through the softmax classifier of the probability prediction model.

[0124] Optionally, the relationship determination module 830 includes: a second generation submodule, used to sort the connection probabilities and generate a probability sequence; a screening submodule, used to sequentially screen the connection probabilities that meet the connection rules from the probability sequence according to the connection rules; and a construction submodule, used to construct a connection relationship between the buoy nodes corresponding to the screened connection probabilities.

[0125] Optionally, the screening submodule includes: a second determination unit, used to sequentially take the connection probabilities in the probability sequence as the target connection probability; a third determination unit, used to determine whether the buoy node corresponding to the target connection probability has formed a single-hop relationship in the previous connection probabilities, and if so, excluding the target connection probability; and a fourth determination unit, used to determine whether the buoy node corresponding to the target connection probability has formed a multi-hop relationship in the previous connection probabilities, and if so, excluding the target connection probability.

[0126] Therefore, according to this embodiment, the satellite determines the connection probability between each buoy node according to the distance between each buoy node and the amount of data transmitted through the probability prediction model, so that the satellite dynamically adjusts the connection relationship between the buoy nodes through the probability prediction model, so that the ocean monitoring buoy network can be optimized more accurately, thereby improving the reliability and speed of data transmission. In addition, this technical solution integrates single-hop and multi-hop connection mechanisms. Compared with the star network in the prior art, this technical solution does not limit the connection relationship between buoy nodes to a single-hop relationship, which not only ensures efficient communication in the local area, but also meets the needs of large-scale data transmission in a large range, effectively overcoming the problem of limited coverage of the traditional star network. In addition, this technical solution screens the connection probability and excludes the connection relationship of repeated connections, avoiding unnecessary data redundancy and bandwidth waste, and does not need to transmit the transmitted data repeatedly through multiple paths, which significantly reduces the network operation cost and reduces the network overhead. In addition, the technical problems of small monitoring range and large network overhead of the ocean monitoring buoy network in the prior art are solved.

[0127] Example 3

[0128] Fig. 9 The satellite-based ocean monitoring buoy network construction device 900 according to this embodiment is shown, and the device 900 corresponds to the method according to the first aspect of embodiment 1. Fig. 9 As shown, the device 900 includes: a processor 910; and a memory 920, which is connected to the processor 910 and is used to provide instructions for the processor 910 to process the following processing steps: obtaining the node distance between each buoy node and the transmission data volume of each buoy node, wherein the transmission data is the ocean monitoring data information collected by the buoy node for transmission to the satellite; determining the connection probability between each buoy node according to the node distance and the transmission data volume through a preset probability prediction model; determining the connection relationship between each buoy node according to the connection probability based on preset connection rules, wherein the connection rule is used to exclude the connection relationship of repeated connection, and wherein the connection relationship includes a single-hop relationship and a multi-hop relationship; and constructing an ocean monitoring buoy network according to the connection relationship.

[0129] Optionally, the operation of determining the connection probability between each buoy node according to the node distance and the amount of transmitted data through a preset probability prediction model includes: generating a first tensor according to the node distance and the amount of transmitted data; and determining the connection probability between each buoy node according to the first tensor through the probability prediction model.

[0130] Optionally, the operation of generating a first tensor based on node distance and transmission data volume includes: generating a first matrix based on the ratio between the transmission data volume of the buoy node and the node distance of the corresponding buoy node; generating a second matrix based on the node distance of each buoy node; and stacking the first matrix and the second matrix to generate a first tensor.

[0131] Optionally, the operation of determining the connection probability between each buoy node based on the first tensor through the probability prediction model includes: performing feature extraction on the first tensor through the encoder-decoder network of the probability prediction model to generate a second tensor, wherein the second tensor is used to indicate the connection integral value and the non-connection integral value between the buoy nodes; and determining the connection probability between each buoy node based on the second tensor through the softmax classifier of the probability prediction model.

[0132] Optionally, the operation of determining the connection relationship between each buoy node based on the connection probability based on a preset connection rule includes: sorting the connection probabilities to generate a probability sequence; filtering the connection probabilities that meet the connection rules from the probability sequence in turn according to the connection rules; and establishing a connection relationship between the buoy nodes corresponding to the filtered connection probabilities.

[0133] Optionally, the operation of sequentially screening connection probabilities that meet the connection rules from the probability sequence according to the connection rules includes: sequentially taking the connection probabilities in the probability sequence as target connection probabilities; determining whether the buoy node corresponding to the target connection probability has formed a single-hop relationship in the previous connection probabilities, and excluding the target connection probability when a single-hop relationship is formed; and determining whether the buoy node corresponding to the target connection probability has formed a multi-hop relationship in the previous connection probabilities, and excluding the target connection probability when a multi-hop relationship is formed.

[0134] Therefore, according to this embodiment, the satellite determines the connection probability between each buoy node according to the distance between each buoy node and the amount of data transmitted through the probability prediction model, so that the satellite dynamically adjusts the connection relationship between the buoy nodes through the probability prediction model, so that the ocean monitoring buoy network can be optimized more accurately, thereby improving the reliability and speed of data transmission. In addition, this technical solution integrates single-hop and multi-hop connection mechanisms. Compared with the star network in the prior art, this technical solution does not limit the connection relationship between buoy nodes to a single-hop relationship, which not only ensures efficient communication in the local area, but also meets the needs of large-scale data transmission in a large range, effectively overcoming the problem of limited coverage of the traditional star network. In addition, this technical solution screens the connection probability and excludes the connection relationship of repeated connections, avoiding unnecessary data redundancy and bandwidth waste, and does not need to transmit the transmitted data repeatedly through multiple paths, which significantly reduces the network operation cost and reduces the network overhead. In addition, the technical problems of small monitoring range and large network overhead of the ocean monitoring buoy network in the prior art are solved.

[0135] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0136] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0137] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0138] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0139] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0140] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk, etc. Various media that can store program codes.

[0141] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for constructing a satellite-based ocean monitoring buoy network, characterized in that: include: Acquire the node distance between each buoy node and the transmission data volume of each buoy node, wherein the transmission data is the ocean monitoring data information collected by the buoy node for transmission to the satellite; Determine the connection probability between the buoy nodes according to the node distance and the amount of transmitted data through a preset probability prediction model; Determining the connection relationship between the buoy nodes according to the connection probability based on a preset connection rule, wherein the connection rule is used to exclude a connection relationship of repeated connection, and wherein the connection relationship includes a single-hop relationship and a multi-hop relationship; and An ocean monitoring buoy network is constructed according to the connection relationship, and wherein The operation of determining the connection probability between the buoy nodes according to the node distance and the amount of transmitted data by using a preset probability prediction model includes: Generate a first tensor according to the node distance and the transmission data amount; and The probability prediction model is used to determine the connection probability between the buoy nodes according to the first tensor, and wherein The operation of generating a first tensor according to the node distance and the amount of transmitted data includes: Generate a first matrix according to the ratio between the transmission data volume of the buoy node and the corresponding node distance of the buoy node; Generate a second matrix according to the node distances of each buoy node; and The first matrix and the second matrix are stacked to generate the first tensor, and wherein The operation of determining the connection probability between the buoy nodes according to the first tensor by using the probability prediction model includes: Performing feature extraction on the first tensor through the encoder-decoder network of the probability prediction model to generate a second tensor, wherein the second tensor is used to indicate the connection integral value and the non-connection integral value between the buoy nodes; and The connection probability between the buoy nodes is determined according to the second tensor through the softmax classifier of the probability prediction model.

2. The method according to claim 1, characterized in that The operation of determining the connection relationship between the buoy nodes according to the connection probability based on a preset connection rule includes: Sorting the connection probabilities to generate a probability sequence; According to the connection rule, connection probabilities that meet the connection rule are sequentially selected from the probability sequence; and The connection relationship is constructed according to the buoy nodes corresponding to the connection probabilities obtained by screening.

3. The method according to claim 2, characterized in that The operation of sequentially selecting connection probabilities that meet the connection rule from the probability sequence according to the connection rule includes: sequentially taking the connection probabilities in the probability sequence as target connection probabilities; Determine whether the buoy node corresponding to the target connection probability has formed a single-hop relationship in the previous connection probabilities, and if the single-hop relationship is formed, exclude the target connection probability; and Determine whether the buoy node corresponding to the target connection probability has formed a multi-hop relationship in the previous connection probability. If the multi-hop relationship is formed, exclude the target connection probability.

4. A satellite-based ocean monitoring buoy network construction device, characterized in that: include: A data acquisition module, used to acquire the node distance between each buoy node and the transmission data volume of each buoy node, wherein the transmission data is the ocean monitoring data information collected by the buoy node for transmission to the satellite; A probability determination module, used to determine the connection probability between the buoy nodes according to the node distance and the amount of transmitted data through a preset probability prediction model; A relationship determination module, configured to determine the connection relationship between the buoy nodes according to the connection probability based on a preset connection rule, wherein the connection rule is used to exclude a connection relationship of repeated connection, and wherein the connection relationship includes a single-hop relationship and a multi-hop relationship; as well as A network generation module is used to construct an ocean monitoring buoy network according to the connection relationship, and wherein The probability determination module includes: a first generation submodule, which is used to generate a first tensor according to the node distance and the amount of transmitted data; and a first determination submodule, which is used to determine the connection probability between the buoy nodes according to the first tensor through the probability prediction model, and wherein The first generating submodule includes: a first generating unit, which is used to generate a first matrix according to the ratio between the transmission data volume of the buoy node and the corresponding node distance of the buoy node; a second generating unit, which is used to generate a second matrix according to the node distance of each buoy node; and a third generating unit, which is used to stack the first matrix and the second matrix to generate the first tensor, and wherein Optionally, the first determination submodule includes: a fourth generation unit, used to perform feature extraction on the first tensor through the codec network of the probability prediction model to generate a second tensor, wherein the second tensor is used to indicate the connection integral value and the non-connection integral value between the buoy nodes; and a first determination unit, used to determine the connection probability between the respective buoy nodes according to the second tensor through the softmax classifier of the probability prediction model.

5. A satellite-based ocean monitoring buoy network construction device, characterized in that: include: processor; as well as A memory, connected to the processor, configured to provide the processor with instructions for processing the following processing steps: Acquire the node distance between each buoy node and the transmission data volume of each buoy node, wherein the transmission data is the ocean monitoring data information collected by the buoy node for transmission to the satellite; Determine the connection probability between the buoy nodes according to the node distance and the amount of transmitted data through a preset probability prediction model; Determining the connection relationship between the buoy nodes according to the connection probability based on a preset connection rule, wherein the connection rule is used to exclude a connection relationship of repeated connection, and wherein the connection relationship includes a single-hop relationship and a multi-hop relationship; and An ocean monitoring buoy network is constructed according to the connection relationship, and wherein The operation of determining the connection probability between the buoy nodes according to the node distance and the amount of transmitted data by using a preset probability prediction model includes: Generate a first tensor according to the node distance and the transmission data amount; and The probability prediction model is used to determine the connection probability between the buoy nodes according to the first tensor, and wherein The operation of generating a first tensor according to the node distance and the amount of transmitted data includes: Generate a first matrix according to the ratio between the transmission data volume of the buoy node and the corresponding node distance of the buoy node; Generate a second matrix according to the node distances of each buoy node; and The first matrix and the second matrix are stacked to generate the first tensor, and wherein The operation of determining the connection probability between the buoy nodes according to the first tensor by using the probability prediction model includes: Performing feature extraction on the first tensor through the encoder-decoder network of the probability prediction model to generate a second tensor, wherein the second tensor is used to indicate the connection integral value and the non-connection integral value between the buoy nodes; and The connection probability between the buoy nodes is determined according to the second tensor through the softmax classifier of the probability prediction model.

6. An integrated electronic system comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method of claim 1.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to claim 1 are implemented.

Images